I'm writing a function to compare the similarity of two strings, using Google's universal sentence encoder. Following the instructions in the notebook provided here I have the following method in my class that takes two sentences as input and prints the similarity between them.
def tf_sim(self, text1, text2):
# Reduce logging output.
tf.logging.set_verbosity(tf.logging.ERROR)
sim_input1 = tf.placeholder(tf.string, shape=(None), name="sim_input1")
sim_input2 = tf.placeholder(tf.string, shape=(None), name="sim_input2")
embedding1 = self.embed([sim_input1])
embedding2 = self.embed([sim_input2])
encode1 = tf.nn.l2_normalize(embedding1, axis=1)
encode2 = tf.nn.l2_normalize(embedding2, axis=1)
sim_scores = -tf.acos(tf.reduce_sum(tf.multiply(encode1, encode2), axis=1))
init_vars = tf.global_variables_initializer()
init_tables = tf.tables_initializer()
with tf.Session() as sess:
sess.run([init_vars, init_tables])
sess.run(sim_scores, feed_dict={sim_input1: text1, sim_input2: text2})
print (sim_scores.eval())
For reference the self.embed attribute looks like this:
self.embed = hub.Module("https://tfhub.dev/google/universal-sentence-encoder/2")
When I call the function:
str1 = "Is Python a better first language to learn than Java"
str2 = "Which of Python or Java is a better programming language to
start out with"
tf_sim(str1, str2)
I get the below stack trace:
Traceback (most recent call last):
File "SimilarityCalculator.py", line 143, in <module>
sc.tf_sim(str1, str2)
File "SimilarityCalculator.py", line 67, in tf_sim
print (sim_scores.eval())
File "/Users/kaushik.visvanathan/anaconda3/envs/Community/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 710, in eval
return _eval_using_default_session(self, feed_dict, self.graph, session)
File "/Users/kaushik.visvanathan/anaconda3/envs/Community/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 5180, in _eval_using_default_session
return session.run(tensors, feed_dict)
File "/Users/kaushik.visvanathan/anaconda3/envs/Community/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 900, in run
run_metadata_ptr)
File "/Users/kaushik.visvanathan/anaconda3/envs/Community/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1135, in _run
feed_dict_tensor, options, run_metadata)
File "/Users/kaushik.visvanathan/anaconda3/envs/Community/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1316, in _do_run
run_metadata)
File "/Users/kaushik.visvanathan/anaconda3/envs/Community/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1335, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: You must feed a value for placeholder tensor 'sim_input1' with dtype string
[[Node: sim_input1 = Placeholder[dtype=DT_STRING, shape=<unknown>, _device="/job:localhost/replica:0/task:0/device:CPU:0"]()]]
Caused by op 'sim_input1', defined at:
File "SimilarityCalculator.py", line 143, in <module>
sc.tf_sim(str1, str2)
File "SimilarityCalculator.py", line 40, in tf_sim
sim_input1 = tf.placeholder(tf.string, shape=(None), name="sim_input1")
File "/Users/kaushik.visvanathan/anaconda3/envs/Community/lib/python3.6/site-packages/tensorflow/python/ops/array_ops.py", line 1808, in placeholder
return gen_array_ops.placeholder(dtype=dtype, shape=shape, name=name)
File "/Users/kaushik.visvanathan/anaconda3/envs/Community/lib/python3.6/site-packages/tensorflow/python/ops/gen_array_ops.py", line 4848, in placeholder
"Placeholder", dtype=dtype, shape=shape, name=name)
File "/Users/kaushik.visvanathan/anaconda3/envs/Community/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "/Users/kaushik.visvanathan/anaconda3/envs/Community/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3392, in create_op
op_def=op_def)
File "/Users/kaushik.visvanathan/anaconda3/envs/Community/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1718, in __init__
self._traceback = self._graph._extract_stack() # pylint: disable=protected-access
InvalidArgumentError (see above for traceback): You must feed a value for placeholder tensor 'sim_input1' with dtype string
[[Node: sim_input1 = Placeholder[dtype=DT_STRING, shape=<unknown>, _device="/job:localhost/replica:0/task:0/device:CPU:0"]()]]
Basically telling me I need to feed a string to the placeholder even though it looks like I'm doing just that. Is there anything I'm missing? Any help is greatly appreciated!
sim_scores.eval()
is equivalent to doing:
sess.run(sim_scores, feed_dict={})
so tensorflow is (rightfully) complaining that you didn't feed sim_input1 (or sim_input2)
Instead store the result of the sess.run() call and print that, or give the feed_dict argument to the eval() call.